INDEX
Explanations
mentions of specific geographical names or terms
New Auto-Interp
Negative Logits
atk
-0.15
culus
-0.14
oze
-0.14
Division
-0.14
Division
-0.14
ë©´
-0.14
ssue
-0.14
765
-0.13
utow
-0.13
cular
-0.13
POSITIVE LOGITS
orget
0.27
elong
0.26
ometric
0.26
ographical
0.25
orges
0.25
ographically
0.23
iger
0.23
auga
0.23
orgetown
0.23
org
0.23
Activations Density 0.021%